Constraint Psychological logo

Constraint Psychological

Community
Deibler
constraint-psychological

Use this skill when designing constraints that work through perception, expectation, and learned convention — symbols, conventions, mappings. Trigger when designing iconography, picking control conventions, or designing for behavioral predictability. Sub-aspect of `constraint`; read that first.

Overview

PublisherDeibler
Repositoryuniversal-design-principles
Skill nameconstraint-psychological
Stars
9
Forks
3
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Deibler on GitHub. Read the source before you install it.

Installation

Install the Constraint Psychological AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Deibler/universal-design-principles/tree/main/plugins/interaction-and-control-principles/skills/constraint-psychological
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Deibler/universal-design-principles.git /tmp/universal-design-principles
mkdir -p .claude/skills
cp -r /tmp/universal-design-principles/plugins/interaction-and-control-principles/skills/constraint-psychological .claude/skills/constraint-psychological
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Constraint Psychological in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Constraint Psychological on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Constraint Psychological is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Psychological constraints

Psychological constraints don't physically prevent action; they make wrong actions feel obviously wrong by leveraging perception, learned convention, or perceived control-effect relationships. Weaker than physical constraints, but available where physical constraints aren't.

The three subtypes (from the book)

Symbols

Communicate meaning through language and imagery. Examples:

  • A skull-and-crossbones on a poison bottle.
  • A "WET FLOOR" sign.
  • A red traffic light.
  • A trash icon on a delete button.

In software UI: any icon or label that signals what an element does or what state it's in. The user reads the symbol and adjusts behavior accordingly.

Conventions

Learned practices that the user expects systems to honor. Examples:

  • "Red means stop, green means go."
  • "Click the X to close."
  • "Cmd-S saves; Cmd-Z undoes."
  • "The hamburger icon opens a menu."

Conventions are powerful because they're transferable — a user who learned cmd-K opens the command palette in one app expects it in others. Honor conventions; deviate only with strong reason.

Mappings

Perceived relationships between controls and their effects. Examples:

  • Stovetop knobs arranged to match burner positions.
  • Volume dial that turns clockwise to increase.
  • Light switches near the lights they control.

In software UI: a row of action buttons whose layout matches the order of objects they affect; a slider whose direction matches the direction of value change.

html
<!-- Mapping: + on the right increases, - on the left decreases -->
<div class="counter">
  <button>−</button>
  <span>5</span>
  <button>+</button>
</div>

Good mapping makes the right action feel obvious; the wrong action feels wrong.

Symbols in software UI

Iconography

Icons that follow established conventions:

  • Trash → delete.
  • Pencil → edit.
  • Magnifier → search.
  • Gear → settings.
  • Bell → notifications.

Reusing conventional icons is psychological constraint via convention. Inventing new icons forces users to learn new symbols; only do so when no convention fits.

Status badges

A red "ERROR" badge psychologically constrains the user from treating the item as normal. The symbol pre-empts the wrong action.

Warning labels

Inline warnings ("This action cannot be undone") constrain the user from proceeding without consideration.

Conventions in software UI

Keyboard conventions

  • Cmd-S / Ctrl-S saves.
  • Cmd-Z / Ctrl-Z undoes.
  • Esc closes overlays.
  • / focuses search.
  • Cmd-K / Ctrl-K opens command palette.

Honoring these conventions constrains the user to expected behavior. Violating them creates surprise.

Mouse conventions

  • Click triggers actions.
  • Right-click opens context menus.
  • Drag moves elements.
  • Hover reveals supplementary information.

Layout conventions

  • Logo top-left links to home.
  • Account menu top-right.
  • Primary action bottom-right of dialogs.
  • "Cancel" left of "Confirm" in dialog footers.

Mappings in software UI

Spatial mappings

  • A list of items in vertical order; the action buttons for each row appear next to each row.
  • A toolbar of formatting buttons; the buttons appear above the text they affect.

Direction mappings

  • Up arrow scrolls up.
  • "Increase" controls increase what they control.
  • A slider moves rightward to increase.

Color mappings

  • Brand color = primary action.
  • Red = destructive.
  • Green = success.

(Color mapping intersects with semantic color systems; see color-semantic-systems.)

When psychological constraints fail

  • First-time users lacking the convention. They don't know cmd-K opens the palette; the constraint doesn't apply.
  • Cross-cultural transfer — symbols and conventions vary by region. Red means luck in some cultures, not danger.
  • Convention drift — old conventions (the floppy-disk save icon) become opaque to younger users.
  • Override by stronger signal — a brand redesign that breaks convention may overpower it.

When psychological constraints fail, fall back to physical constraints (block the wrong action structurally) or explicit information (explain the rules).

Anti-patterns

  • Custom icons that violate conventions — the user's prior knowledge becomes wrong.
  • Convention-breaking shortcuts — Cmd-S that triggers something other than save.
  • Arbitrary mappings — buttons that don't correspond spatially to what they affect.
  • Cultural-blind symbols — a hand gesture icon that means OK in one culture and offense in another.

Heuristics

  1. The convention audit. For each interactive element, name the convention you're following or breaking. Breaking should be deliberate.
  2. The "what does this symbol mean?" check. Show your icons to users unfamiliar with your product. If they can't tell, the symbol isn't carrying its psychological constraint.
  3. The mapping check. For each control, do its position and direction match the effect? If not, mapping is failing.

Related sub-skills

  • constraint (parent).
  • constraint-physical — the structural complement.
  • mapping (cognition) — the broader principle.
  • mimicry — psychological constraints often borrow from familiar systems.
  • expectation-effect — convention-honoring designs match user expectations.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Constraint Psychological AI skill do?

Use this skill when designing constraints that work through perception, expectation, and learned convention — symbols, conventions, mappings. Trigger when designing iconography, picking control conventions, or designing for behavioral predictability. Sub-aspect of `constraint`; read that first.

Why use Constraint Psychological on TypingMind?

Because you install it once and use it with any model. Constraint Psychological is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Constraint Psychological in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Deibler/universal-design-principles/tree/main/plugins/interaction-and-control-principles/skills/constraint-psychological. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Constraint Psychological?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Constraint Psychological?

As many as you like. As long as a model supports skills, you can use Constraint Psychological with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Constraint Psychological AI skill free?

It is published on GitHub by Deibler. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇